v1.6.1: Ray dependency and seq_length improvements (#253)

* Ray is an optional dependency now.
* seq_length cleanup and adding warnings for using deprecated seq_len config name for RNN networks

v1.6.0

• Added ONNX export colab example for discrete and continuous action spaces. For continuous case LSTM policy example is provided as well.
• Improved RNNs training in continuous space, added option zero_rnn_on_done.
• Added NVIDIA CuLE support: https://github.com/NVlabs/cule
• Added player config override. Vecenv is used for inference.
• Fixed multi-gpu training with central value.
• Fixed max_frames termination condition, and it's interaction with the linear learning rate: #212
• Fixed "deterministic" misspelling issue.
• Fixed Mujoco and Brax SAC configs.
• Fixed multiagent envs statistics reporting. Fixed Starcraft2 SMAC environments.

Full Changelog: v1.5.2...v1.6.0

v1.0-alpha2: Merge pull request #30 from Denys88/vm/ray_and_installation_updates

Fixed Ray 1.0 API. Updated requirements.

v1.0-alpha

Updated requirements.txt